© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 64988
    Prev
    Next
    INDEX
    Explanations

    build commands

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects references to GNU make (e.g. the “make” command or Makefile and related file tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ining
    -1.29
     hua
    -1.27
    >//
    -1.20
    嘥
    -1.20
    的男人
    -1.20
    vičius
    -1.16
    ﹶ
    -1.16
    phinx
    -1.16
    ㎏
    -1.14
    <0x00>
    -1.13
    POSITIVE LOGITS
     it
    1.89
     Geschä
    1.42
     totalité
    1.34
     your
    1.27
                    
    1.26
     Hinblick
    1.24
     selben
    1.23
    1
    1.23
     Gerichte
    1.22
    >
    1.21
    Activations Density 0.073%

    No Known Activations